Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53e30b72785b346184d3120f8c5476d6e7b280d6710807d55b60c7c41e631317
+oid sha256:3646a1015329fa974db54936473db010722eca2c610e0ffdbd4418ff87e4202d
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc9f8889cd91caf9aa46130e12a9dcefe7d23be5bf4d2d63fde7677f4bdd5c14
+oid sha256:ca6ec5b095f1fce71efad1224a65bb72a80b8baacd49fcb326862786d9a398f9
 size 27273018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b520d868492a9d95066915a515f10685b9502d0f7289232878d7c778af4698ef
+oid sha256:729c7f2d902c60105070255d20eb6f294b0b37a328e908e81bee80cfa849183d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cef7bf070e527a9b5896b7711e9e6af634052f75dbe8f4acb6da29f40d856bc6
+oid sha256:8d8615f1aeccd0f9873fc0cf2c0322fde20ac202421c015654a471730a5fa755
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.13020833333333334,
+  "epoch": 0.2604166666666667,
   "eval_steps": 9,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -206,6 +206,205 @@
       "learning_rate": 1.866025403784439e-05,
       "loss": 2.9082,
       "step": 25
+    },
+    {
+      "epoch": 0.13541666666666666,
+      "grad_norm": 0.7362732887268066,
+      "learning_rate": 1.848048096156426e-05,
+      "loss": 2.9769,
+      "step": 26
+    },
+    {
+      "epoch": 0.140625,
+      "grad_norm": 0.6465035080909729,
+      "learning_rate": 1.8290375725550417e-05,
+      "loss": 2.946,
+      "step": 27
+    },
+    {
+      "epoch": 0.140625,
+      "eval_loss": 2.9850566387176514,
+      "eval_runtime": 2.1389,
+      "eval_samples_per_second": 75.74,
+      "eval_steps_per_second": 9.818,
+      "step": 27
+    },
+    {
+      "epoch": 0.14583333333333334,
+      "grad_norm": 0.6484801769256592,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 2.9388,
+      "step": 28
+    },
+    {
+      "epoch": 0.15104166666666666,
+      "grad_norm": 0.6423029899597168,
+      "learning_rate": 1.788010753606722e-05,
+      "loss": 2.874,
+      "step": 29
+    },
+    {
+      "epoch": 0.15625,
+      "grad_norm": 0.641499936580658,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 2.961,
+      "step": 30
+    },
+    {
+      "epoch": 0.16145833333333334,
+      "grad_norm": 0.669302225112915,
+      "learning_rate": 1.7431448254773943e-05,
+      "loss": 2.918,
+      "step": 31
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 0.5931358933448792,
+      "learning_rate": 1.7193398003386514e-05,
+      "loss": 2.9327,
+      "step": 32
+    },
+    {
+      "epoch": 0.171875,
+      "grad_norm": 0.6197303533554077,
+      "learning_rate": 1.6946583704589973e-05,
+      "loss": 2.8986,
+      "step": 33
+    },
+    {
+      "epoch": 0.17708333333333334,
+      "grad_norm": 0.5762773752212524,
+      "learning_rate": 1.6691306063588583e-05,
+      "loss": 2.8925,
+      "step": 34
+    },
+    {
+      "epoch": 0.18229166666666666,
+      "grad_norm": 0.5871465802192688,
+      "learning_rate": 1.6427876096865394e-05,
+      "loss": 2.9471,
+      "step": 35
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 0.6552653312683105,
+      "learning_rate": 1.6156614753256583e-05,
+      "loss": 2.9724,
+      "step": 36
+    },
+    {
+      "epoch": 0.1875,
+      "eval_loss": 2.9104537963867188,
+      "eval_runtime": 2.0723,
+      "eval_samples_per_second": 78.172,
+      "eval_steps_per_second": 10.133,
+      "step": 36
+    },
+    {
+      "epoch": 0.19270833333333334,
+      "grad_norm": 0.6476786732673645,
+      "learning_rate": 1.5877852522924733e-05,
+      "loss": 2.9259,
+      "step": 37
+    },
+    {
+      "epoch": 0.19791666666666666,
+      "grad_norm": 0.6450286507606506,
+      "learning_rate": 1.5591929034707468e-05,
+      "loss": 2.8913,
+      "step": 38
+    },
+    {
+      "epoch": 0.203125,
+      "grad_norm": 0.5890446901321411,
+      "learning_rate": 1.529919264233205e-05,
+      "loss": 2.9457,
+      "step": 39
+    },
+    {
+      "epoch": 0.20833333333333334,
+      "grad_norm": 0.6238468885421753,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 2.8409,
+      "step": 40
+    },
+    {
+      "epoch": 0.21354166666666666,
+      "grad_norm": 0.5730621814727783,
+      "learning_rate": 1.469471562785891e-05,
+      "loss": 2.7774,
+      "step": 41
+    },
+    {
+      "epoch": 0.21875,
+      "grad_norm": 0.5432677268981934,
+      "learning_rate": 1.4383711467890776e-05,
+      "loss": 2.8458,
+      "step": 42
+    },
+    {
+      "epoch": 0.22395833333333334,
+      "grad_norm": 0.5576301217079163,
+      "learning_rate": 1.4067366430758004e-05,
+      "loss": 2.888,
+      "step": 43
+    },
+    {
+      "epoch": 0.22916666666666666,
+      "grad_norm": 0.5752390027046204,
+      "learning_rate": 1.3746065934159123e-05,
+      "loss": 2.8943,
+      "step": 44
+    },
+    {
+      "epoch": 0.234375,
+      "grad_norm": 0.5436639785766602,
+      "learning_rate": 1.342020143325669e-05,
+      "loss": 2.8378,
+      "step": 45
+    },
+    {
+      "epoch": 0.234375,
+      "eval_loss": 2.8462777137756348,
+      "eval_runtime": 2.0769,
+      "eval_samples_per_second": 78.0,
+      "eval_steps_per_second": 10.111,
+      "step": 45
+    },
+    {
+      "epoch": 0.23958333333333334,
+      "grad_norm": 0.5786373615264893,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 2.8375,
+      "step": 46
+    },
+    {
+      "epoch": 0.24479166666666666,
+      "grad_norm": 0.5880608558654785,
+      "learning_rate": 1.2756373558169992e-05,
+      "loss": 2.8433,
+      "step": 47
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.5975544452667236,
+      "learning_rate": 1.2419218955996677e-05,
+      "loss": 2.7899,
+      "step": 48
+    },
+    {
+      "epoch": 0.2552083333333333,
+      "grad_norm": 0.5674802660942078,
+      "learning_rate": 1.2079116908177592e-05,
+      "loss": 2.8498,
+      "step": 49
+    },
+    {
+      "epoch": 0.2604166666666667,
+      "grad_norm": 0.5659404397010803,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 2.8706,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 506757189206016.0,
+  "total_flos": 1020456257716224.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null